CN113853629A - Power grid user classification method and device and computer readable storage medium - Google Patents

Power grid user classification method and device and computer readable storage medium Download PDF

Info

Publication number
CN113853629A
CN113853629A CN201980096605.6A CN201980096605A CN113853629A CN 113853629 A CN113853629 A CN 113853629A CN 201980096605 A CN201980096605 A CN 201980096605A CN 113853629 A CN113853629 A CN 113853629A
Authority
CN
China
Prior art keywords
user
time
electricity consumption
time period
particles
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201980096605.6A
Other languages
Chinese (zh)
Inventor
李昂
李晶
刘浩
王丹
华文韬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens AG
Original Assignee
Siemens AG
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens AG filed Critical Siemens AG
Publication of CN113853629A publication Critical patent/CN113853629A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
    • G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/018—Certifying business or products
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/20—Pc systems
    • G05B2219/26—Pc applications
    • G05B2219/2639—Energy management, use maximum of cheap power, keep peak load low
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
    • Y04S50/14—Marketing, i.e. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Tourism & Hospitality (AREA)
  • Educational Administration (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Health & Medical Sciences (AREA)
  • Automation & Control Theory (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The embodiment of the invention discloses a power grid user classification method, a device and a computer readable storage medium. The method comprises the following steps: determining user electricity data for each time period within a time interval, wherein the user electricity data for each time period comprises the user electricity data for each time particle within the time period; generating a power consumption mode image of the user in the time interval based on the power consumption data of the user in each time period in the time interval; and classifying the user based on the image recognition result of the power utilization pattern image. Through carrying out image recognition to the power consumption mode image in order to classify the user, need not to fill in archives information by hand, can reduce manual work load. Moreover, the completeness defect caused by incomplete archive information is avoided, and the classification accuracy can be improved.

Description

Power grid user classification method and device and computer readable storage medium Technical Field
The invention relates to the technical field of electric power, in particular to a power grid user classification method, a device and a computer readable storage medium.
Background
Currently, there is a high demand for customer management of the power grid. For example, electricity stealing detection becomes more and more prominent, which not only troubles the development of power supply enterprises, but also seriously affects the national economic construction and social stability, and users are generally required to be classified according to the industry in order to identify electricity stealing behaviors.
In the current power grid user management, users are classified into industries mainly based on archive information manually filled in when the users register. However, manually filled-in profile information is not necessarily accurate due to human factor participation, which may result in inaccurate user classification results. In addition, manually filling in profile information also increases the workload of the user.
Disclosure of Invention
The embodiment of the invention provides a power grid user classification method, a device and a computer readable storage medium, and reduces manual workload.
The technical scheme of the embodiment of the invention is as follows:
the power grid user classification method comprises the following steps:
determining user electricity data for each time period within a time interval, wherein the user electricity data for each time period comprises the user electricity data for each time particle within the time period;
generating a power consumption mode image of the user in the time interval based on the power consumption data of the user in each time period in the time interval;
and classifying the user based on the image recognition result of the power utilization pattern image.
Therefore, the embodiment of the invention classifies the user by carrying out image recognition on the electricity consumption mode image without manually filling in archive information, thereby reducing the manual workload. In addition, the embodiment of the invention also avoids the integrity defect caused by incomplete archive information and can improve the classification accuracy.
In one embodiment, the generating an electricity consumption pattern image of the user in a time interval based on the electricity consumption data of the user in each time period in the time interval includes: displaying the user electricity consumption data of all the time particles in each time period according to the color characteristics corresponding to the numerical value of the user electricity consumption data in a coordinate system with time periods on the horizontal axis and time particles on the vertical axis to generate an electricity consumption mode image of the user; the classifying the user based on the image recognition result of the power consumption pattern image comprises: extracting color features of the electricity consumption mode image, and classifying the user based on the color features.
Therefore, the electricity consumption pattern image includes color features corresponding to the numerical values of the electricity consumption data of the user, and the user can be conveniently classified based on the extracted color features. In addition, in the power consumption pattern image including the color feature, the power consumption data is displayed by using time dimensions such as time particles, time periods, time intervals and the like, the amount of the user behavior feature is large, and a good classification result can be obtained.
In one embodiment, the generating an electricity consumption pattern image of the user in a time interval based on the electricity consumption data of the user in each time period in the time interval includes: displaying the user electricity consumption data of all the time particles in each time period according to the shape characteristics corresponding to the numerical values of the user electricity consumption data in a coordinate system with time periods on the horizontal axis and time particles on the vertical axis to generate an electricity consumption mode image of the user; the classifying the user based on the image recognition result of the power consumption pattern image comprises: and extracting shape features of the power utilization pattern image, and classifying the user based on the shape features.
Therefore, the power consumption pattern image includes shape features corresponding to the numerical values of the power consumption data of the user, and the user can be conveniently classified based on the extracted shape features. Moreover, in the power consumption pattern image including the shape feature, the power consumption data is displayed by using time dimensions such as time particles, time periods, time intervals and the like, the amount of the user behavior feature is large, and a good classification result can be obtained.
In one embodiment, the generating an electricity consumption pattern image of the user in a time interval based on the electricity consumption data of the user in each time period in the time interval includes: displaying the user electricity consumption data of all the time particles in each time period according to the texture characteristics corresponding to the numerical value of the user electricity consumption data in a coordinate system with time periods on the horizontal axis and time particles on the vertical axis to generate an electricity consumption mode image of the user; the classifying the user based on the image recognition result of the power consumption pattern image comprises: extracting texture features of the electricity consumption mode image, and classifying the user based on the texture features.
Therefore, the electricity consumption mode image includes texture features corresponding to the numerical values of the electricity consumption data of the user, and the user can be conveniently classified based on the extracted texture features. Moreover, in the electricity consumption mode image containing the texture features, the electricity consumption data are displayed by using time dimensions such as time particles, time periods, time intervals and the like, the amount of the user behavior feature is large, and a good classification result can be obtained.
In one embodiment, the generating an electricity consumption pattern image of the user in a time interval based on the electricity consumption data of the user in each time period in the time interval includes: displaying the user electricity consumption data of all the time particles in each time period according to the spatial relationship characteristics of the numerical value corresponding to the user electricity consumption data in a coordinate system with time periods on the horizontal axis and time particles on the vertical axis to generate an electricity consumption mode image of the user; the classifying the user based on the image recognition result of the power consumption pattern image comprises: and extracting spatial relation characteristics of the electricity consumption mode images, and classifying the user based on the spatial relation characteristics.
Therefore, the electricity consumption pattern image includes the spatial relationship feature corresponding to the numerical value of the electricity consumption data of the user, and the user can be conveniently classified based on the extracted spatial relationship feature. Moreover, in the electricity consumption mode image containing the spatial relationship characteristics, the electricity consumption data are displayed by using time dimensions such as time particles, time periods and time intervals, the amount of the user behavior characteristic is large, and a good classification result can be obtained.
In one embodiment, the time particle is an hour, the time period is a day, and the time interval is a week; or
The time particles are hours, the time period is days, and the time interval is months; or
The time particles are hours, the time period is days, and the time interval is quarterly; or
The time particles are hours, the time period is days, and the time interval is years; or
The time particles are minutes, the time period is hours, and the time interval is days; or
The time particles are minutes, the time period is hours, and the time interval is weeks; or
The time particles are minutes, the time period is hours, and the time interval is months; or
The time particles are minutes, the time period is hours, and the time interval is quarterly; or
The time particles are minutes, the time period is hours, and the time interval is years.
It can be seen that the time particles, time periods and time intervals have various embodiments for easy selection by the user.
Electric wire netting user classification device includes:
the power utilization data determining module is used for determining user power utilization data of each time period in a time interval, wherein the user power utilization data of each time period comprise the user power utilization data of each time particle in the time period;
the image generation module is used for generating an electricity utilization mode image of the user in the time interval based on the electricity utilization data of the user in each time period in the time interval;
and the classification module is used for classifying the users based on the image recognition result of the power utilization pattern image.
Therefore, the embodiment of the invention classifies the user by carrying out image recognition on the electricity consumption mode image without manually filling in archive information, thereby reducing the manual workload. In addition, the embodiment of the invention also avoids the integrity defect caused by incomplete archive information and can improve the classification accuracy.
In one embodiment, the image generating module is configured to display the user electricity consumption data of all the time particles in each time period according to a color feature corresponding to a numerical value of the user electricity consumption data in a coordinate system with a time period on a horizontal axis and a time particle on a vertical axis to generate the electricity consumption mode image of the user; the classification module is used for extracting color features of the electricity consumption mode images and classifying the users based on the color features.
Therefore, the electricity consumption pattern image includes color features corresponding to the numerical values of the electricity consumption data of the user, and the user can be conveniently classified based on the extracted color features. Moreover, in the electricity consumption mode image containing the color features, the electricity consumption data are displayed by using time dimensions such as time particles, time periods, time intervals and the like, the amount of the user behavior feature is large, and a good classification result can be obtained.
In one embodiment, the image generating module is configured to display the user electricity consumption data of all the time particles in each time period according to shape features corresponding to the numerical size of the user electricity consumption data in a coordinate system with a time period on a horizontal axis and a time particle on a vertical axis to generate the electricity consumption mode image of the user; the classification module is used for extracting shape features of the power utilization pattern image and classifying the user based on the shape features.
Therefore, the power consumption pattern image includes shape features corresponding to the numerical values of the power consumption data of the user, and the user can be conveniently classified based on the extracted shape features. Moreover, in the power consumption pattern image including the shape feature, the power consumption data is displayed by using time dimensions such as time particles, time periods, time intervals and the like, the amount of the user behavior feature is large, and a good classification result can be obtained.
In one embodiment, the image generating module is configured to display, in a coordinate system with a time period on a horizontal axis and a time particle on a vertical axis, the user electricity consumption data of all the time particles in each time period according to a texture feature corresponding to a numerical value of the user electricity consumption data, so as to generate the electricity consumption mode image of the user; the classification module is used for extracting texture features of the electricity consumption mode images and classifying the users based on the texture features.
Therefore, the electricity consumption mode image includes texture features corresponding to the numerical values of the electricity consumption data of the user, and the user can be conveniently classified based on the extracted texture features. Moreover, in the electricity consumption mode image containing the texture features, the electricity consumption data are displayed by using time dimensions such as time particles, time periods, time intervals and the like, the amount of the user behavior feature is large, and a good classification result can be obtained.
In one embodiment, the image generating module is configured to display, in a coordinate system with a time period on a horizontal axis and a time particle on a vertical axis, the user electricity consumption data of all the time particles in each time period according to a spatial relationship characteristic corresponding to a numerical value of the user electricity consumption data, so as to generate the electricity consumption mode image of the user; the classification module is used for extracting the spatial relationship characteristics of the power consumption mode images and classifying the users based on the spatial relationship characteristics.
Therefore, the electricity consumption pattern image includes the spatial relationship feature corresponding to the numerical value of the electricity consumption data of the user, and the user can be conveniently classified based on the extracted spatial relationship feature. Moreover, in the electricity consumption mode image containing the spatial relationship characteristics, the electricity consumption data are displayed by using time dimensions such as time particles, time periods and time intervals, the amount of the user behavior characteristic is large, and a good classification result can be obtained.
The power grid user classification device comprises a processor and a memory;
the memory stores an application program executable by the processor for causing the processor to perform the grid user classification method as described in any one of the above.
A computer readable storage medium having stored therein computer readable instructions for performing the grid user classification method as described in any of the above.
A computer program product tangibly stored on a computer-readable medium and comprising computer-executable instructions that, when executed, cause at least one processor to perform a power grid user classification method according to any one of claims 1 to 6.
Drawings
Fig. 1 is a flowchart of a power grid user classification method according to an embodiment of the present invention.
FIG. 2 is an exemplary diagram of time intervals, time periods, and time particles for an embodiment of the present invention.
Fig. 3 is a first exemplary diagram of a power consumption mode image according to an embodiment of the invention.
Fig. 4 is a second exemplary diagram of a power consumption mode image according to an embodiment of the invention.
Fig. 5 is a schematic diagram illustrating a comparison between a power grid user classification processing procedure according to an embodiment of the present invention and a power grid user classification processing procedure in the prior art.
Fig. 6 is a structural diagram of a power grid user classification device according to an embodiment of the present invention.
Fig. 7 is a block diagram of a grid user classification device of a processor-memory structure according to an embodiment of the present invention.
Wherein the reference numbers are as follows:
reference numerals Means of
101～103 Step (ii) of
501 User' s
502 Archive information
503 Reliability defect
504 Integrity defect
505 Electricity data
506 Electricity usage curve
507 Defect of characteristic loss
508 Power mode image
509 Classification result
600 Power grid user classification device
601 Electricity consumption data determination module
602 Image generation module
603 Classification module
700 Electricity consumption data determination module
701 Processor with a memory having a plurality of memory cells
702 Memory device
Detailed Description
In order to make the technical scheme and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the detailed description and specific examples, while indicating the scope of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
For simplicity and clarity of description, the invention will be described below by describing several representative embodiments. Numerous details of the embodiments are set forth to provide an understanding of the principles of the invention. It will be apparent, however, that the invention may be practiced without these specific details. Some embodiments are not described in detail, but rather are merely provided as frameworks, in order to avoid unnecessarily obscuring aspects of the invention. Hereinafter, "including" means "including but not limited to", "according to … …" means "at least according to … …, but not limited to … … only". In view of the language convention of chinese, the following description, when it does not specifically state the number of a component, means that the component may be one or more, or may be understood as at least one.
In consideration of the defects that users are classified based on archive information manually filled during user registration in the prior art, the embodiment of the invention provides a technical scheme for classifying the users by carrying out image recognition on the electricity consumption mode images, so that the manual workload can be reduced, and the classification accuracy can be improved.
Fig. 1 is a flowchart of a power grid user classification method according to an embodiment of the present invention.
As shown in fig. 1, the method includes:
step 101: determining user electricity data for each time segment within a time interval, wherein the user electricity data for each time segment comprises the user electricity data for each time particle within the time segment.
Here, the time interval, time period and time particle are all time measurement units. Wherein: the duration of the time interval is greater than the duration of the time period, which is greater than the duration of the time particles. The time interval includes a plurality of time segments, and each time segment includes a plurality of time particles.
FIG. 2 is an exemplary diagram of time intervals, time periods, and time particles for an embodiment of the present invention.
As can be seen from fig. 2, the time interval T1 comprises a plurality of time segments T2, each time segment T2 comprising a plurality of time particles T3.
The time interval, the time period and the time granules can be implemented as natural time such as natural year, natural month or natural day, or can be implemented as freely set time units.
For example, the time interval may be implemented as weeks, the time period may be implemented as days, and the time particles may be implemented as hours. One time interval (one week) contained 7 time segments, each time segment (one day) contained 24 time particles (hours). At this time, in step 101, based on the smart meter reading of the grid user or the electricity database stored in the cloud, the electricity consumption data (e.g., electricity consumption) of the user for 24 hours per day in 1 week is determined.
For example, the time interval may be implemented as a month, the time period may be implemented as a day, and the time particles may be implemented as hours. A time interval (one month) may for example contain 30 time segments, each time segment (one day) containing 24 time particles (hours). At this time, in step 101, based on the smart meter reading of the grid user or the electricity database stored in the cloud, the electricity consumption data (e.g., electricity consumption) of the user for 24 hours per day in 1 month is determined.
For example, the time interval may be implemented as a quarter, the time period may be implemented as a day, and the time particle may be implemented as an hour. A time interval (one quarter) may for example comprise 90 time segments, each time segment (one day) comprising 24 time particles (hours). At this time, in step 101, based on the smart meter reading of the grid user or the electricity database stored in the cloud, the electricity consumption data (e.g., electricity consumption) of the user for 24 hours per day in 1 quarter is determined.
For example, the time interval may be implemented as years, the time period may be implemented as days, and the time particles may be implemented as hours. A time interval (one quarter) may for example comprise 365 time segments, each time segment (one day) comprising 24 time particles (hours). At this time, in step 101, based on the smart meter reading of the grid user or the electricity database stored in the cloud, the electricity consumption data (e.g., electricity consumption) of the user for 24 hours per day in 1 year is determined.
For example, the time interval may be implemented as days, the time period may be implemented as hours, and the time particles may be implemented as minutes. One time interval (one day) contained 24 time periods, each time period (one hour) contained 60 time particles (minutes). At this time, in step 101, the electricity consumption data (e.g., electricity consumption) of the user per minute within 1 day is determined based on the smart meter reading of the grid user or the electricity consumption database stored in the cloud.
For example, the time interval may be implemented as weeks, the time period may be implemented as hours, and the time particles may be implemented as minutes. One time interval (one week) contained 168 time periods, each time period (one hour) containing 60 time particles (minutes). At this time, in step 101, the electricity consumption data (e.g., electricity consumption) of the user per minute within 1 week is determined based on the smart meter reading of the grid user or the electricity consumption database stored in the cloud.
For example, the time interval may be implemented as a month, the time period may be implemented as an hour, and the time particles may be implemented as minutes. A time interval (january) may for example comprise 720 time segments, each time segment (hour) comprising 60 time particles (minutes). At this time, in step 101, the electricity consumption data (e.g., electricity consumption) of the user per minute within 1 month is determined based on the smart meter reading of the grid user or the electricity consumption database stored in the cloud.
For example, the time interval may be implemented as a quarter, the time period may be implemented as hours, and the time particles may be implemented as minutes. A time interval (one quarter) may for example contain 2160 time periods, each time period (one hour) containing 60 time particles (minutes). At this time, in step 101, based on the smart meter reading of the grid user, the electricity consumption data (e.g., electricity consumption) of the user per minute for 1 quarter is determined.
For example, the time interval may be implemented as years, the time period may be implemented as hours, and the time particles may be implemented as minutes. A time interval (one year) may for example contain 8760 time segments, each time segment (one hour) containing 60 time particles (minutes). At this time, in step 101, based on the smart meter reading of the grid user, user electricity consumption data (e.g., electricity consumption) per minute within 1 year is determined.
While the above exemplary descriptions of time intervals, time periods, and time particles and representative examples of obtaining user power usage data are provided, those skilled in the art will appreciate that such descriptions are merely exemplary and are not intended to limit the scope of embodiments of the present invention.
Step 102: and generating a power utilization pattern image of the user in the time interval based on the power utilization data of the user in each time period in the time interval.
Here, the power consumption pattern image of the user in the time interval is generated based on the power consumption data of the user in each time period in the time interval acquired in step 101. The generated electricity consumption pattern image includes image features corresponding to the numerical value of the electricity consumption data of the user.
Preferably, the numerical value of the user electricity consumption data may be represented by using image features such as color features, texture features, shape features, and spatial relationship features.
In one embodiment, step 102 comprises: and displaying the user electricity consumption data of all the time particles in each time period according to the color characteristics corresponding to the numerical values of the user electricity consumption data in a coordinate system with time periods on the horizontal axis and time particles on the vertical axis so as to generate an electricity consumption mode image of the user. Such as: the corresponding relation between the color characteristics and the numerical value of the electricity consumption data comprises the following steps: red indicates that the numerical value of the user electricity utilization data is in a high interval; orange indicates that the numerical value of the user electricity utilization data is in a middle interval; and green indicates that the numerical value of the electricity consumption data of the user is in a low interval.
In one embodiment, step 102 comprises: and displaying the user electricity consumption data of all the time particles in each time period according to the shape characteristics corresponding to the numerical values of the user electricity consumption data in a coordinate system with time periods on the horizontal axis and time particles on the vertical axis so as to generate an electricity consumption mode image of the user. Such as: the correspondence between the shape characteristics and the numerical values of the electricity consumption data includes: the triangle indicates that the numerical value of the user electricity utilization data is in a high interval; the square indicates that the numerical value of the user electricity utilization data is in a middle interval; the circle indicates that the numerical value of the user electricity consumption data is in a low interval.
In one embodiment, step 102 comprises: and displaying the user electricity consumption data of all the time particles in each time period according to the texture characteristics corresponding to the numerical value of the user electricity consumption data in a coordinate system with time periods on the horizontal axis and time particles on the vertical axis so as to generate an electricity consumption mode image of the user. Such as: the corresponding relation between the texture features and the numerical value of the electricity consumption data comprises the following steps: the crack indicates that the numerical value of the electricity utilization data of the user is in a high interval; the mosaic tiling texture represents that the numerical value of the user electricity consumption data is in a medium interval; the grain texture indicates that the numerical value of the user electricity consumption data is in a low interval.
In one embodiment, step 102 comprises: and in a coordinate system with time periods on the horizontal axis and time particles on the vertical axis, displaying the user electricity consumption data of all the time particles in each time period according to the spatial relationship characteristics corresponding to the numerical values of the user electricity consumption data so as to generate an electricity consumption mode image of the user. Such as: the corresponding relation between the spatial relation characteristics and the numerical value of the electricity utilization data comprises the following steps: the connection/adjacency relation and the numerical value representing the user electricity consumption data are in a high interval; the overlapping/overlapping relation indicates that the numerical value of the user electricity utilization data is in a medium interval; the containing/containing relation indicates that the numerical value of the user electricity consumption data is in a low interval.
The above exemplary descriptions of the typical example of the image feature and the corresponding relationship between the image feature and the numerical value of the power consumption data are exemplary, and it can be appreciated by those skilled in the art that the description is only exemplary and is not intended to limit the scope of the embodiments of the present invention.
Next, a description will be given of an example in which a power consumption pattern image including a color feature indicating the numerical value of user power consumption data is generated.
Fig. 3 is a first exemplary diagram of a power consumption mode image according to an embodiment of the invention.
As shown in fig. 3, in a coordinate system in which the horizontal axis (D axis) is day and the vertical axis (H axis) is hour, the time interval is week (including 7 days), the time period is day, and the time particle is hour.
Firstly, based on the reading of the smart meter of the power grid user or a power utilization database stored in the cloud, the power consumption of the user within one week and 24 hours per day is obtained.
Then, based on the numerical value of the used amount of electricity for 24 hours per day within one week, the display colors of the respective pixel areas corresponding to each hour within each day within one week are determined.
Specifically, the method comprises the following steps:
the display color of the pixel area D1H1 in the coordinate system is determined based on the numerical magnitude of the used amount of electricity for the first hour (H1) on the first day (D1). Wherein: if the used amount of electricity for the first hour (H1) in the first day (D1) is in the high section, the pixel area D1H1 is shown as red; if the power usage for the first hour (H1) on the first day (D1) is in the middle interval, the pixel region D1H1 is shown as orange; if the used amount of electricity for the first hour (H1) in the first day (D1) is in the low section, the pixel area D1H1 is shown as green.
The display color of the pixel area D1H2 in the coordinate system is determined based on the numerical magnitude of the used amount of electricity for the second hour (H2) on the first day (D1). Likewise: if the used amount of electricity for the second hour (H2) in the first day (D1) is in the high section, the pixel area D1H2 is shown as red; if the power usage for the second hour (H2) on the first day (D1) is in the middle interval, the pixel region D1H2 is shown as orange; if the used amount of electricity for the second hour (H2) in the first day (D1) is in the low section, the pixel area D1H2 is shown as green.
The display color of the pixel area D1H3 in the coordinate system is determined based on the numerical magnitude of the used amount of electricity for the third hour (H3) on the first day (D1). Likewise: if the used amount of electricity for the third hour (H3) in the first day (D1) is in the high section, the pixel area D1H3 is shown as red; if the power usage for the third hour (H2) on the first day (D1) is in the middle interval, the pixel region D1H3 is shown as orange; if the used amount of electricity for the third hour (H3) in the first day (D1) is in the low section, the pixel area D1H3 is shown as green.
By analogy, the display colors of the pixel regions corresponding to the fourth hour (H4) on the first day (D1) and the fifth hour (H5) … on the first day (D1) are continuously determined until the display color of the pixel region D1H24 in the coordinate system is determined based on the numerical value of the power consumption of the twenty-fourth hour (H24) on the first day (D1). Likewise: if the power usage at the twenty-fourth hour (H24) on the first day (D1) is in the high section, the pixel area D1H24 is shown as red; if the power usage at the twenty-fourth hour (H2) on the first day (D1) is in the middle interval, the pixel region D1H24 is shown as orange; if the used amount of electricity at the twenty-fourth hour (H24) on the first day (D1) is in a low section, the pixel area D1H24 is shown to be green.
At this point, the color determination of the pixel area for the entire 24 hours of the first day is completed.
And then, by analogy, completing the color determination of the pixel regions for the respective total 24 hours on the second day and the third day, so as to complete the color determination of all the pixel regions within one week.
The image finally formed based on the above manner is the power consumption mode image within one week, and the color feature included in the user mode image represents the numerical value of the user power consumption data of each time particle in each time period in the time interval.
Next, a description will be given by taking an example of generating a power consumption pattern image including a shape feature indicating a numerical value of user power consumption data.
Fig. 4 is a second exemplary diagram of a power consumption mode image according to an embodiment of the invention.
As shown in fig. 4, in a coordinate system in which the horizontal axis (H axis) is hours and the vertical axis (M axis) is minutes, the time interval is days (including 24 hours), the time period is hours (including 60 minutes), and the time particle is minutes.
Firstly, based on the reading of the smart meter of the power grid user or a power utilization database stored in the cloud, the power consumption of the user per minute in each hour within one day is obtained.
Then, based on the numerical magnitude of the used amount of electricity per minute in each hour within one day, the presentation shapes corresponding to the respective pixel areas per minute in each hour within one day are determined.
Specifically, the method comprises the following steps:
the display shape of the pixel region H1M1 in the coordinate system is determined based on the numerical magnitude of the used amount of electricity for the first minute (M1) within the first hour (H1). Wherein: if the used amount of the electricity for the first minute (M1) in the first hour (H1) is in the high section, the pixel region H1M1 shows a triangle; if the used amount of the electricity for the first minute (M1) in the first hour (H1) is in the middle section, the pixel region H1M1 is shown as a square; if the used amount of the first minute (M1) in the first hour (H1) is in the low section, the pixel region H1M1 is shown as a circle.
The display shape of the pixel region H1M2 in the coordinate system is determined based on the numerical magnitude of the used amount of electricity for the second minute (M2) within the first hour (H1). Likewise: if the used amount of electricity for the second minute (M2) in the first hour (H1) is in the high section, the pixel region H1M2 shows a triangle; if the used amount of electricity for the second minute (M2) in the first hour (H1) is in the middle section, the pixel region H1M2 is shown as a square; if the used amount of the second minute (M2) in the first hour (H1) is in the low section, the pixel region H1M2 is shown as a circle.
The display shape of the pixel region H1M3 in the coordinate system is determined based on the numerical magnitude of the used amount of electricity for the third minute (M3) within the first hour (H1). Likewise: if the used amount of the electricity for the third minute (M3) in the first hour (H1) is in the high section, the pixel region H1M3 shows a triangle; if the used amount of electricity for the third minute (M3) in the first hour (H1) is in the middle section, the pixel region H1M3 is shown as a square; if the used amount of the electricity for the third minute (M3) in the first hour (H1) is in the low section, the pixel region H1M3 is shown as a circle.
And so on, determining the display color of the corresponding respective pixel regions at the fourth minute (M4) in the first hour (H1), at the fifth minute (M5) in the first hour (H1), until determining the display shape of the pixel region H1M60 in the coordinate system based on the numerical magnitude of the power usage at the sixty minute (M60) in the first hour (H1). Likewise: if the used amount of electricity for the sixty-th minute (M60) in the first hour (H1) is in the high section, the pixel region H1M60 shows a triangle; if the power usage for the sixty-th minute (M60) in the first hour (H1) is in the middle interval, the pixel region H1M60 is shown as a square; if the used amount of the sixty-th minute (M1) in the first hour (H1) is in the low section, the pixel region H1M60 is shown as a circle.
At this point, the shape determination of the pixel region for the entire 60 minutes in the first hour is completed. Then, and so on, the shape determination of the pixel area for all 60 minutes each in the second hour, the third hour.
Based on the above manner, the finally formed image is the power consumption mode image in one day, and the shape feature included in the user mode image represents the numerical value of the user power consumption data of each time particle in each time period in the time interval.
In the above, the typical example of generating the electricity consumption mode image including the image feature representing the numerical value of the electricity consumption data of the user is described by taking the image feature as the color feature and the shape feature as an example, and those skilled in the art can appreciate that the electricity consumption mode image including the image feature such as the texture feature or the spatial relationship feature may also be generated in a similar manner, and the embodiment of the present invention is not limited thereto.
Step 103: and classifying the users based on the image recognition result of the power utilization pattern image.
Here, image features are extracted from the power pattern image using an image recognition technique, and the user is classified based on the extracted image features.
When the power mode image contains color features, step 103 comprises: and extracting color features of the power utilization pattern image, and classifying the user based on the color features. When the power pattern image contains shape features, step 103 comprises: and extracting shape features of the power utilization pattern image, and classifying the user based on the shape features. When the power mode image contains texture features, step 103 comprises: and extracting texture features of the electricity consumption mode image, and classifying users based on the texture features. When the electricity consumption mode image contains the spatial relationship feature, step 103 includes: and extracting the spatial relationship characteristics of the power utilization pattern image, and classifying the users based on the spatial relationship characteristics.
For example, a machine learning mode, a fractal feature mode or a wavelet moment mode can be adopted to extract image features and user classification, and the like. In the machine learning mode, supervised learning, unsupervised learning, semi-supervised learning or clustering algorithm can be adopted to realize user classification.
In one embodiment, a feature template corresponding to the industry attribute is preset, and the extracted image features are compared with the feature template to determine the industry classification of the user.
In one embodiment, a convolutional neural network is trained based on training samples, and the industry classification of the user is determined by inputting the extracted image features into the convolutional neural network.
In one embodiment, the extracted image features are clustered based on a K-means equal clustering algorithm to determine the industry classification of the user.
While the above exemplary description describes specific ways of implementing user classification, those skilled in the art will appreciate that this description is merely exemplary and is not intended to limit the scope of embodiments of the present invention.
Fig. 5 is a schematic diagram illustrating a comparison between a power grid user classification processing procedure according to an embodiment of the present invention and a power grid user classification processing procedure in the prior art.
In fig. 5, a user 501 is typically classified based on profile information 502 in the prior art. This classification has a reliability deficiency 503 and an integrity deficiency 504, since the manually filled-in profile information is not necessarily accurate and not necessarily complete.
Power usage data 505 may be collected for the user 501. There are also prior art ways to classify the electricity usage curves 506 generated based on the user data 505. However, the power utilization curve 506 can only show the power utilization data in one time dimension, and the user behavior is characterized in a single manner, so that the classification method has the defect of missing features 507.
In an embodiment of the present invention, power usage data 505 is collected for a user 501 and classified based on the user data 505 and time intervals, time periods, and time granularity divisions to generate a power usage pattern image 508. In the electricity consumption mode image 508, the electricity consumption data is displayed by using time dimensions such as time particles, time periods, time intervals and the like, the user behavior characteristics are more, and a good industry classification result 509 can be obtained.
Based on the above description, the embodiment of the invention also provides a power grid user classification device.
Fig. 6 is a structural diagram of a power grid user classification device according to an embodiment of the present invention.
As shown in fig. 6, the grid user classification device 600 includes:
the power utilization data determining module 601 is configured to determine user power utilization data of each time period in a time interval, where the user power utilization data of each time period includes the user power utilization data of each time particle in the time period;
an image generating module 602, configured to generate an electricity consumption pattern image of the user in a time interval based on the user electricity consumption data in each time period in the time interval;
the classifying module 603 is configured to classify the user based on an image recognition result of the power consumption pattern image.
In one embodiment, the image generating module 602 is configured to display the user electricity consumption data of all the time particles in each time period according to a color feature corresponding to a numerical value of the user electricity consumption data in a coordinate system with a time period on a horizontal axis and a time particle on a vertical axis to generate an electricity consumption pattern image of the user; and the classification module 603 is configured to extract color features of the power consumption pattern image, and classify the user based on the color features.
In one embodiment, the image generating module 601 is configured to display the user electricity consumption data of all the time particles in each time period according to shape features corresponding to the numerical size of the user electricity consumption data in a coordinate system with a horizontal axis as the time period and a vertical axis as the time particles to generate an electricity consumption pattern image of the user; a classification module 602, configured to extract shape features of the power consumption pattern image, and classify the user based on the shape features.
In one embodiment, the image generating module 601 is configured to display, in a coordinate system with a time period on a horizontal axis and a time granule on a vertical axis, the user power consumption data of all the time granules in each time period according to a texture feature corresponding to a numerical value of the user power consumption data, so as to generate a power consumption pattern image of a user; a classification module 602, configured to extract texture features of the power consumption mode image, and classify the user based on the texture features.
In one embodiment, the image generating module 601 is configured to display the user electricity consumption data of all the time particles in each time period according to a spatial relationship characteristic corresponding to a numerical value of the user electricity consumption data in a coordinate system with a horizontal axis as the time period and a vertical axis as the time particles, so as to generate an electricity consumption mode image of the user; the classification module 602 is configured to extract spatial relationship features of the power consumption pattern image, and classify the user based on the spatial relationship features.
The embodiment of the invention also provides a power grid user classification device with a processor and a memory structure.
Fig. 7 is a block diagram of a grid user classification device of a processor-memory structure according to an embodiment of the present invention.
As shown in fig. 7, the grid user classification apparatus 700 includes a processor 701 and a memory 702;
the memory 702 stores an application program executable by the processor 701, and is used for causing the processor 701 to execute the power consumption abnormality identification method according to any one of the above embodiments.
The memory 702 may be embodied as various storage media such as an Electrically Erasable Programmable Read Only Memory (EEPROM), a flash memory (flash memory), and a Programmable Read Only Memory (PROM). The processor 701 may be implemented to include one or more central processors or one or more field programmable gate arrays, wherein the field programmable gate arrays integrate one or more central processor cores. In particular, the central processor or central processor core may be implemented as a CPU or MCU.
It should be noted that not all steps and modules in the above flows and system structure diagrams are necessary, and some steps or modules may be omitted according to actual needs. The execution order of the steps is not fixed and can be adjusted as required. The system structure described in the above embodiments may be a physical structure or a logical structure, that is, some modules may be implemented by the same physical entity, or some modules may be implemented by a plurality of physical entities, or some components in a plurality of independent devices may be implemented together.
The hardware modules in the various embodiments may be implemented mechanically or electronically. For example, a hardware module may include a specially designed permanent circuit or logic device (e.g., a special purpose processor such as an FPGA or ASIC) for performing specific operations. A hardware module may also include programmable logic devices or circuits (e.g., including a general-purpose processor or other programmable processor) that are temporarily configured by software to perform certain operations. The implementation of the hardware module in a mechanical manner, or in a dedicated permanent circuit, or in a temporarily configured circuit (e.g., configured by software), may be determined based on cost and time considerations.
The present invention also provides a machine-readable storage medium storing instructions for causing a machine to perform a method as described herein. Specifically, a system or an apparatus equipped with a storage medium on which a software program code that realizes the functions of any of the embodiments described above is stored may be provided, and a computer (or a CPU or MPU) of the system or the apparatus is caused to read out and execute the program code stored in the storage medium. Further, part or all of the actual operations may be performed by an operating system or the like operating on the computer by instructions based on the program code. The functions of any of the above-described embodiments may also be implemented by writing the program code read out from the storage medium to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion unit connected to the computer, and then causing a CPU or the like mounted on the expansion board or the expansion unit to perform part or all of the actual operations based on the instructions of the program code.
Examples of the storage medium for supplying the program code include floppy disks, hard disks, magneto-optical disks, optical disks (e.g., CD-ROMs, CD-R, CD-RWs, DVD-ROMs, DVD-RAMs, DVD-RWs, DVD + RWs), magnetic tapes, nonvolatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or the cloud by a communication network.
A computer program product, presented in embodiments of the invention, tangibly stored on a computer-readable medium and comprising computer-executable instructions that, when executed, cause at least one processor to perform a power grid user classification method according to any of claims 1 to 6.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (14)

  1. The power grid user classification method is characterized by comprising the following steps:
    determining user electricity data for each time segment within a time interval, wherein the user electricity data for each time segment comprises user electricity data for each time particle within the time segment (101);
    generating a power consumption mode image (102) of the user in the time interval based on the user power consumption data of each time period in the time interval;
    classifying (103) the user based on an image recognition result of the power pattern image.
  2. The grid user classification method according to claim 1,
    the method for generating the power consumption mode image (102) of the user in the time interval based on the power consumption data of the user in each time period in the time interval comprises the following steps: displaying the user electricity consumption data of all the time particles in each time period according to the color characteristics corresponding to the numerical value of the user electricity consumption data in a coordinate system with time periods on the horizontal axis and time particles on the vertical axis to generate an electricity consumption mode image of the user;
    the classifying (103) the user based on the image recognition result of the power consumption pattern image includes: extracting color features of the electricity consumption mode image, and classifying the user based on the color features.
  3. The grid user classification method according to claim 1,
    the method for generating the power consumption mode image (102) of the user in the time interval based on the power consumption data of the user in each time period in the time interval comprises the following steps: displaying the user electricity consumption data of all the time particles in each time period according to the shape characteristics corresponding to the numerical values of the user electricity consumption data in a coordinate system with time periods on the horizontal axis and time particles on the vertical axis to generate an electricity consumption mode image of the user;
    the classifying (103) the user based on the image recognition result of the power consumption pattern image includes: and extracting shape features of the power utilization pattern image, and classifying the user based on the shape features.
  4. The grid user classification method according to claim 1,
    the method for generating the power consumption mode image (102) of the user in the time interval based on the power consumption data of the user in each time period in the time interval comprises the following steps: displaying the user electricity consumption data of all the time particles in each time period according to the texture characteristics corresponding to the numerical value of the user electricity consumption data in a coordinate system with time periods on the horizontal axis and time particles on the vertical axis to generate an electricity consumption mode image of the user;
    the classifying (103) the user based on the image recognition result of the power consumption pattern image includes: extracting texture features of the electricity consumption mode image, and classifying the user based on the texture features.
  5. The grid user classification method according to claim 1,
    the method for generating the power consumption mode image (102) of the user in the time interval based on the power consumption data of the user in each time period in the time interval comprises the following steps: displaying the user electricity consumption data of all the time particles in each time period according to the spatial relationship characteristics of the numerical value corresponding to the user electricity consumption data in a coordinate system with time periods on the horizontal axis and time particles on the vertical axis to generate an electricity consumption mode image of the user;
    the classifying (103) the user based on the image recognition result of the power consumption pattern image includes: and extracting spatial relation characteristics of the electricity consumption mode images, and classifying the user based on the spatial relation characteristics.
  6. The grid user classification method according to any of claims 1-5,
    the time particles are hours, the time period is days, and the time interval is weeks; or
    The time particles are hours, the time period is days, and the time interval is months; or
    The time particles are hours, the time period is days, and the time interval is quarterly; or
    The time particles are hours, the time period is days, and the time interval is years; or
    The time particles are minutes, the time period is hours, and the time interval is days; or
    The time particles are minutes, the time period is hours, and the time interval is weeks; or
    The time particles are minutes, the time period is hours, and the time interval is months; or
    The time particles are minutes, the time period is hours, and the time interval is quarterly; or
    The time particles are minutes, the time period is hours, and the time interval is years.
  7. Grid user classification device (600), characterized in that it comprises:
    the power utilization data determining module (601) is used for determining user power utilization data of each time period in a time interval, wherein the user power utilization data of each time period comprise the user power utilization data of each time particle in the time period;
    an image generation module (602) for generating an electricity consumption pattern image of the user in the time interval based on the user electricity consumption data of each time period in the time interval;
    a classification module (603) for classifying the user based on an image recognition result of the power consumption pattern image.
  8. The grid user classification device (600) according to claim 7,
    the image generation module (602) is configured to display the user electricity consumption data of all the time particles in each time period according to a color feature corresponding to the numerical value of the user electricity consumption data in a coordinate system with a time period on a horizontal axis and a time particle on a vertical axis so as to generate an electricity consumption mode image of the user;
    the classification module (603) is used for extracting color features of the electricity consumption mode image and classifying the user based on the color features.
  9. The grid user classification device (600) according to claim 7,
    the image generation module (602) is configured to display the user electricity consumption data of all the time particles in each time period according to shape features corresponding to the numerical values of the user electricity consumption data in a coordinate system with a time period on a horizontal axis and a time particle on a vertical axis so as to generate an electricity consumption mode image of the user;
    the classification module (603) is used for extracting shape features of the power utilization pattern image and classifying the user based on the shape features.
  10. The grid user classification device (600) according to claim 7,
    the image generation module (602) is configured to display the user electricity consumption data of all the time particles in each time period according to a texture feature corresponding to the numerical value of the user electricity consumption data in a coordinate system with a time period on a horizontal axis and a time particle on a vertical axis so as to generate an electricity consumption mode image of the user;
    the classification module (603) is used for extracting texture features of the electricity consumption mode image and classifying the user based on the texture features.
  11. The grid user classification device (600) according to claim 7,
    the image generation module (602) is configured to display the user electricity consumption data of all the time particles in each time period according to a spatial relationship characteristic corresponding to the magnitude of the numerical value of the user electricity consumption data in a coordinate system with a time period on a horizontal axis and a time particle on a vertical axis, so as to generate an electricity consumption mode image of the user;
    the classification module (603) is configured to extract spatial relationship features of the power consumption mode image, and classify the user based on the spatial relationship features.
  12. Grid user classification apparatus (700), characterized by comprising a processor (701) and a memory (702);
    the memory (702) has stored therein an application executable by the processor (701) for causing the processor (701) to perform the grid user classification method according to any of claims 1 to 6.
  13. Computer-readable storage medium, characterized in that computer-readable instructions are stored therein for performing the grid user classification method according to any of claims 1 to 6.
  14. A computer program product tangibly stored on a computer-readable medium and comprising computer-executable instructions that, when executed, cause at least one processor to perform a power grid user classification method according to any one of claims 1 to 6.
CN201980096605.6A 2019-05-29 2019-05-29 Power grid user classification method and device and computer readable storage medium Pending CN113853629A (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/089103 WO2020237540A1 (en) 2019-05-29 2019-05-29 Power grid user classification method and device, and computer-readable storage medium

Publications (1)

Publication Number Publication Date
CN113853629A true CN113853629A (en) 2021-12-28

Family

ID=73553033

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201980096605.6A Pending CN113853629A (en) 2019-05-29 2019-05-29 Power grid user classification method and device and computer readable storage medium

Country Status (4)

Country Link
US (1) US20220236706A1 (en)
EP (1) EP3961548A4 (en)
CN (1) CN113853629A (en)
WO (1) WO2020237540A1 (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020252784A1 (en) * 2019-06-21 2020-12-24 西门子股份公司 Power load data prediction method and device, and storage medium
CN112488590B (en) * 2020-12-21 2022-12-30 青岛海尔科技有限公司 Target object classification method and device, storage medium and electronic device
CN117239739B (en) * 2023-11-13 2024-02-02 国网冀北电力有限公司 Method, device and equipment for predicting user side load by knowledge big model

Family Cites Families (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5552995A (en) * 1993-11-24 1996-09-03 The Trustees Of The Stevens Institute Of Technology Concurrent engineering design tool and method
JP2003189471A (en) * 2001-12-12 2003-07-04 Mitsubishi Electric Corp Power user data analysis method
US7369950B2 (en) * 2003-02-07 2008-05-06 Power Measurement Ltd. System and method for power quality analytics
US8538484B2 (en) * 2009-08-14 2013-09-17 Google Inc. Providing a user with feedback regarding power consumption in battery-operated electronic devices
JP5803249B2 (en) * 2011-05-06 2015-11-04 ソニー株式会社 Information processing apparatus, information processing method, and program
CA2948240A1 (en) * 2012-01-20 2013-08-25 Neurio Technology, Inc. System and method of compiling and organizing power consumption data and converting such data into one or more user actionable formats
US9906028B2 (en) * 2012-11-20 2018-02-27 Siemens Aktiengesellschaft Method and system for operating an electrical energy supply network
KR20140091331A (en) * 2013-01-11 2014-07-21 송암시스콤 주식회사 Automatic meter reading system
US9256271B2 (en) * 2013-10-04 2016-02-09 American Megatrends, Inc. Predictive power management based on user category
EP3095261B1 (en) * 2014-01-15 2020-04-08 Telefonaktiebolaget LM Ericsson (publ) Method, apparatus, online charging system, computer program and computer program product for subscription adaptation
JP6474782B2 (en) * 2014-03-07 2019-02-27 株式会社日立製作所 Data analysis system and method
FI125264B (en) * 2014-03-13 2015-08-14 Op Palvelut Oy Content selection for mobile device
US20160018835A1 (en) * 2014-07-18 2016-01-21 Retroficiency, Inc. System and method for virtual energy assessment of facilities
KR101570144B1 (en) * 2014-07-28 2015-11-18 한국전력공사 Apparatus and method for analyzing metering information
US10175276B2 (en) * 2014-11-26 2019-01-08 Sense Labs, Inc. Identifying and categorizing power consumption with disaggregation
CN105183753A (en) * 2015-07-14 2015-12-23 深圳库博能源科技有限公司 Electricity consumption data visualization method, electricity consumption data visualization device and mobile terminal
JP6672803B2 (en) * 2016-01-08 2020-03-25 株式会社リコー Liquid ejection device, liquid ejection method, and program
US20170205868A1 (en) * 2016-01-19 2017-07-20 Tatung Company Method of analyzing power usage and electronic apparatus thereof
US20170309196A1 (en) * 2016-04-21 2017-10-26 Microsoft Technology Licensing, Llc User energy-level anomaly detection
CN106599034A (en) * 2016-11-04 2017-04-26 国网浙江省电力公司 Power grid enterprise power balance data visualization system and method
JP2020510945A (en) * 2017-02-13 2020-04-09 グリディ ホールディングス エルエルシーＧｒｉｄｄｙ Ｈｏｌｄｉｎｇｓ Ｌｌｃ Method and system for automation of a platform for a utility-related market
US20200034768A1 (en) * 2017-03-10 2020-01-30 Bizen Green Energy Corporation Energy conservation diagnostic system, method and program
CN107294093A (en) * 2017-07-26 2017-10-24 广东电网有限责任公司电力科学研究院 Electric power data analysis method, device and intelligent terminal based on K line charts
CN108765188A (en) * 2018-05-02 2018-11-06 深圳供电局有限公司 A kind of graphical real-time energy efficiency monitoring system
CN108959424B (en) * 2018-06-11 2021-08-20 长春电力设计有限公司 Operation method of urban electricity utilization map for monitoring load of power system
US11211792B2 (en) * 2018-07-06 2021-12-28 Schneider Electric USA, Inc. Supplemental techniques for characterizing power quality events in an electrical system
CN109325537A (en) * 2018-09-26 2019-02-12 深圳供电局有限公司 Power consumption management method, apparatus, computer equipment and storage medium
CN109308306B (en) * 2018-09-29 2021-07-06 重庆大学 User power consumption abnormal behavior detection method based on isolated forest
CN113853623A (en) * 2019-05-29 2021-12-28 西门子股份公司 Power load prediction method, device and storage medium
KR102100449B1 (en) * 2019-07-02 2020-05-15 나성진 Method for prediction natural ingredients of cosmetic and apparatus for performing the same
US11397020B2 (en) * 2019-07-05 2022-07-26 Lg Electronics Inc. Artificial intelligence based apparatus and method for forecasting energy usage

Also Published As

Publication number Publication date
EP3961548A4 (en) 2022-11-30
WO2020237540A1 (en) 2020-12-03
US20220236706A1 (en) 2022-07-28
EP3961548A1 (en) 2022-03-02

Similar Documents

Publication Publication Date Title
CN113853629A (en) Power grid user classification method and device and computer readable storage medium
US9064151B2 (en) Device and method for detecting plantation rows
CN104166841A (en) Rapid detection identification method for specified pedestrian or vehicle in video monitoring network
CN113853528A (en) Power utilization abnormality recognition method, device and computer readable storage medium
CN111177208A (en) Power consumption abnormity detection method based on big data analysis
CN116229007B (en) Four-dimensional digital image construction method, device, equipment and medium using BIM modeling
CN116720984A (en) Intelligent electric power auditing method based on satellite map technology
CA3043672A1 (en) A method of predicting a traffic behaviour in a road system
CN115660262B (en) Engineering intelligent quality inspection method, system and medium based on database application
Zhang et al. A framework for automated construction of building models from airborne Lidar measurements
CA3046873A1 (en) A method of predicting a traffic behaviour in a road system
CN110688900A (en) Withdrawal meter management method based on image recognition
CN114819941A (en) Method and device for generating study-leaving user payment life cycle model
CN114328495A (en) Enterprise material cleaning service system and data cleaning method thereof
CN111460293B (en) Information pushing method and device and computer readable storage medium
CN106651630B (en) Crucial electricity consumption industry recognition methods and system
CN116611678B (en) Data processing method, device, computer equipment and storage medium
CN115757987B (en) Method, device, equipment and medium for determining companion object based on track analysis
WO2019196502A1 (en) Marketing activity quality assessment method, server, and computer readable storage medium
CN115951295A (en) Automatic identification method and system for daily clear power abnormity
CN114676931B (en) Electric quantity prediction system based on data center technology
CN110175199A (en) Energy enterprise key user's identifying and analyzing method based on K mean cluster algorithm
CN114240924A (en) Power grid equipment quality evaluation method based on digitization technology
CN113869269A (en) Activity site congestion degree detection method and device, electronic equipment and storage medium
CN113434680A (en) User intention analysis method and device based on seat data and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination